We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 545d69c commit f5d3349Copy full SHA for f5d3349
tests/ut/attention/test_mla_v1.py
@@ -454,10 +454,11 @@ def setUp(self):
454
mock_model_config.get_head_size.return_value = 64
455
mock_model_config.dtype = torch.float16
456
457
+ from vllm.config.scheduler import SchedulerConfig
458
+ self.mock_vllm_config.scheduler_config = SchedulerConfig()
459
+
460
self.mock_vllm_config.model_config = mock_model_config
461
self.mock_vllm_config.cache_config = MagicMock(block_size=16)
- self.mock_vllm_config.scheduler_config = MagicMock(
- max_num_seqs=4, enable_chunked_prefill=False)
462
self.mock_vllm_config.speculative_config = None
463
464
self.mock_device = torch.device('cpu')
0 commit comments